@article{cattell2011scalable, title={Scalable SQL and NoSQL data stores}, author={Cattell, Rick}, journal={ACM SIGMOD Record}, volume={39}, number={4}, pages={12--27}, year={2011}, publisher={ACM} } @article{chang2008bigtable, title={Bigtable: A distributed storage system for structured data}, author={Chang, Fay and Dean, Jeffrey and Ghemawat, Sanjay and Hsieh, Wilson C and Wallach, Deborah A and Burrows, Mike and Chandra, Tushar and Fikes, Andrew and Gruber, Robert E}, journal={ACM Transactions on Computer Systems (TOCS)}, volume={26}, number={2}, pages={4}, year={2008}, publisher={ACM} } @inproceedings{decandia2007dynamo, title={Dynamo: amazon's highly available key-value store}, author={DeCandia, Giuseppe and Hastorun, Deniz and Jampani, Madan and Kakulapati, Gunavardhan and Lakshman, Avinash and Pilchin, Alex and Sivasubramanian, Swaminathan and Vosshall, Peter and Vogels, Werner}, booktitle={ACM SIGOPS Operating Systems Review}, volume={41}, number={6}, pages={205--220}, year={2007}, organization={ACM} } @inproceedings{abadi2008column, title={Column-Stores vs. Row-Stores: How different are they really?}, author={Abadi, Daniel J and Madden, Samuel R and Hachem, Nabil}, booktitle={Proceedings of the 2008 ACM SIGMOD international conference on Management of data}, pages={967--980}, year={2008}, organization={ACM} } @inproceedings{bear2012vertica, title={The vertica database: SQL RDBMS for managing big data}, author={Bear, Chuck and Lamb, Andrew and Tran, Nga}, booktitle={Proceedings of the 2012 workshop on Management of big data systems}, pages={37--38}, year={2012}, organization={ACM} } @article{lakshman2010cassandra, title={Cassandra—A decentralized structured storage system}, author={Lakshman, Avinash and Malik, Prashant}, journal={Operating systems review}, volume={44}, number={2}, pages={35}, year={2010} } @article{melnik2010dremel, title={Dremel: interactive analysis of web-scale datasets}, author={Melnik, Sergey and Gubarev, Andrey and Long, Jing Jing and Romer, Geoffrey and Shivakumar, Shiva and Tolton, Matt and Vassilakis, Theo}, journal={Proceedings of the VLDB Endowment}, volume={3}, number={1-2}, pages={330--339}, year={2010}, publisher={VLDB Endowment} } @article{hall2012processing, title={Processing a trillion cells per mouse click}, author={Hall, Alexander and Bachmann, Olaf and B{\"u}ssow, Robert and G{\u{a}}nceanu, Silviu and Nunkesser, Marc}, journal={Proceedings of the VLDB Endowment}, volume={5}, number={11}, pages={1436--1446}, year={2012}, publisher={VLDB Endowment} } @inproceedings{shvachko2010hadoop, title={The hadoop distributed file system}, author={Shvachko, Konstantin and Kuang, Hairong and Radia, Sanjay and Chansler, Robert}, booktitle={Mass Storage Systems and Technologies (MSST), 2010 IEEE 26th Symposium on}, pages={1--10}, year={2010}, organization={IEEE} } @article{colantonio2010concise, title={Concise: Compressed ‘n’Composable Integer Set}, author={Colantonio, Alessandro and Di Pietro, Roberto}, journal={Information Processing Letters}, volume={110}, number={16}, pages={644--650}, year={2010}, publisher={Elsevier} } @inproceedings{stonebraker2005c, title={C-store: a column-oriented DBMS}, author={Stonebraker, Mike and Abadi, Daniel J and Batkin, Adam and Chen, Xuedong and Cherniack, Mitch and Ferreira, Miguel and Lau, Edmond and Lin, Amerson and Madden, Sam and O'Neil, Elizabeth and others}, booktitle={Proceedings of the 31st international conference on Very large data bases}, pages={553--564}, year={2005}, organization={VLDB Endowment} } @article{stonebraker1987extendability, title={Extendability in POSTGRES.}, author={Stonebraker, Michael and Anton, Jeff and Hirohama, Michael}, journal={IEEE Data Eng. Bull.}, volume={10}, number={2}, pages={16--23}, year={1987} } @book{george2011hbase, title={HBase: the definitive guide}, author={George, Lars}, year={2011}, publisher={" O'Reilly Media, Inc."} } @inproceedings{engle2012shark, title={Shark: fast data analysis using coarse-grained distributed memory}, author={Engle, Cliff and Lupher, Antonio and Xin, Reynold and Zaharia, Matei and Franklin, Michael J and Shenker, Scott and Stoica, Ion}, booktitle={Proceedings of the 2012 international conference on Management of Data}, pages={689--692}, year={2012}, organization={ACM} } @inproceedings{zaharia2012discretized, title={Discretized streams: an efficient and fault-tolerant model for stream processing on large clusters}, author={Zaharia, Matei and Das, Tathagata and Li, Haoyuan and Shenker, Scott and Stoica, Ion}, booktitle={Proceedings of the 4th USENIX conference on Hot Topics in Cloud Computing}, pages={10--10}, year={2012}, organization={USENIX Association} } @misc{marz2013storm, author = {Marz, Nathan}, title = {Storm: Distributed and Fault-Tolerant Realtime Computation}, month = {February}, year = {2013}, howpublished = "\url{http://storm-project.net/}" } @misc{2014samza, title = {Apache Samza}, year = {2014}, howpublished = "\url{http://samza.apache.org/}" } @misc{2013linkedin, title = {Camus}, year = {2013}, howpublished = "\url{https://github.com/linkedin/camus}" } @misc{yang2014radstack, title = {Real Time Analytics with Open Source Technologies}, year = {2014}, howpublished = "\url{https://speakerdeck.com/druidio/real-time-analytics-with-open-source-technologies-1}" } @inproceedings{yang2014druid, title={Druid: a real-time analytical data store}, author={Yang, Fangjin and Tschetter, Eric and L{\'e}aut{\'e}, Xavier and Ray, Nelson and Merlino, Gian and Ganguli, Deep}, booktitle={Proceedings of the 2014 ACM SIGMOD international conference on Management of data}, pages={157--168}, year={2014}, organization={ACM} } @misc{2014yahoo, title = {Pushing the limits of Realtime Analytics using Druid}, year = {2014}, howpublished = "\url{http://www.slideshare.net/ydn/pushing-thelimitsofrealtimeanalyticswithdruidv3}" } @misc{tschetter2011druid, author = {Eric Tschetter}, title = {Introducing Druid: Real-Time Analytics at a Billion Rows Per Second}, month = {April}, year = {2011}, howpublished = "\url{http://druid.io/blog/2011/04/30/introducing-druid.html}" } @article{farber2012sap, title={SAP HANA database: data management for modern business applications}, author={F{\"a}rber, Franz and Cha, Sang Kyun and Primsch, J{\"u}rgen and Bornh{\"o}vd, Christof and Sigg, Stefan and Lehner, Wolfgang}, journal={ACM Sigmod Record}, volume={40}, number={4}, pages={45--51}, year={2012}, publisher={ACM} } @misc{voltdb2010voltdb, title={VoltDB Technical Overview}, author={VoltDB, LLC}, year={2010}, howpublished = "\url{https://voltdb.com/}" } @inproceedings{macnicol2004sybase, title={Sybase IQ multiplex-designed for analytics}, author={MacNicol, Roger and French, Blaine}, booktitle={Proceedings of the Thirtieth international conference on Very large data bases-Volume 30}, pages={1227--1230}, year={2004}, organization={VLDB Endowment} } @inproceedings{singh2011introduction, title={Introduction to the IBM Netezza warehouse appliance}, author={Singh, Malcolm and Leonhardi, Ben}, booktitle={Proceedings of the 2011 Conference of the Center for Advanced Studies on Collaborative Research}, pages={385--386}, year={2011}, organization={IBM Corp.} } @inproceedings{miner2012unified, title={Unified analytics platform for big data}, author={Miner, Donald}, booktitle={Proceedings of the WICSA/ECSA 2012 Companion Volume}, pages={176--176}, year={2012}, organization={ACM} } @inproceedings{fink2012distributed, title={Distributed computation on dynamo-style distributed storage: riak pipe}, author={Fink, Bryan}, booktitle={Proceedings of the eleventh ACM SIGPLAN workshop on Erlang workshop}, pages={43--50}, year={2012}, organization={ACM} } @misc{paraccel2013, key = {ParAccel Analytic Database}, title = {ParAccel Analytic Database}, month = {March}, year = {2013}, howpublished = "\url{http://www.paraccel.com/resources/Datasheets/ParAccel-Core-Analytic-Database.pdf}" } @misc{cloudera2013, key = {Cloudera Impala}, title = {Cloudera Impala}, month = {March}, year = {2013}, url = {}, howpublished = "\url{http://blog.cloudera.com/blog}" } @inproceedings{hunt2010zookeeper, title={ZooKeeper: Wait-free coordination for Internet-scale systems}, author={Hunt, Patrick and Konar, Mahadev and Junqueira, Flavio P and Reed, Benjamin}, booktitle={USENIX ATC}, volume={10}, year={2010} } @inproceedings{kreps2011kafka, title={Kafka: A distributed messaging system for log processing}, author={Kreps, Jay and Narkhede, Neha and Rao, Jun}, booktitle={Proceedings of 6th International Workshop on Networking Meets Databases (NetDB), Athens, Greece}, year={2011} } @misc{liblzf2013, title = {LibLZF}, key = {LibLZF}, month = {March}, year = {2013}, howpublished = "\url{http://freecode.com/projects/liblzf}" } @inproceedings{tomasic1993performance, title={Performance of inverted indices in shared-nothing distributed text document information retrieval systems}, author={Tomasic, Anthony and Garcia-Molina, Hector}, booktitle={Parallel and Distributed Information Systems, 1993., Proceedings of the Second International Conference on}, pages={8--17}, year={1993}, organization={IEEE} } @inproceedings{antoshenkov1995byte, title={Byte-aligned bitmap compression}, author={Antoshenkov, Gennady}, booktitle={Data Compression Conference, 1995. DCC'95. Proceedings}, pages={476}, year={1995}, organization={IEEE} } @inproceedings{van2011memory, title={A memory efficient reachability data structure through bit vector compression}, author={van Schaik, Sebastiaan J and de Moor, Oege}, booktitle={Proceedings of the 2011 international conference on Management of data}, pages={913--924}, year={2011}, organization={ACM} } @inproceedings{o1993lru, title={The LRU-K page replacement algorithm for database disk buffering}, author={O'neil, Elizabeth J and O'neil, Patrick E and Weikum, Gerhard}, booktitle={ACM SIGMOD Record}, volume={22}, number={2}, pages={297--306}, year={1993}, organization={ACM} } @article{kim2001lrfu, title={LRFU: A spectrum of policies that subsumes the least recently used and least frequently used policies}, author={Kim, Chong Sang}, journal={IEEE Transactions on Computers}, volume={50}, number={12}, year={2001} } @article{wu2006optimizing, title={Optimizing bitmap indices with efficient compression}, author={Wu, Kesheng and Otoo, Ekow J and Shoshani, Arie}, journal={ACM Transactions on Database Systems (TODS)}, volume={31}, number={1}, pages={1--38}, year={2006}, publisher={ACM} } @misc{twitter2013, key = {Twitter Public Streams}, title = {Twitter Public Streams}, month = {March}, year = {2013}, howpublished = "\url{https://dev.twitter.com/docs/streaming-apis/streams/public}" } @article{fitzpatrick2004distributed, title={Distributed caching with memcached}, author={Fitzpatrick, Brad}, journal={Linux journal}, number={124}, pages={72--74}, year={2004} } @inproceedings{amdahl1967validity, title={Validity of the single processor approach to achieving large scale computing capabilities}, author={Amdahl, Gene M}, booktitle={Proceedings of the April 18-20, 1967, spring joint computer conference}, pages={483--485}, year={1967}, organization={ACM} } @book{sarawagi1998discovery, title={Discovery-driven exploration of OLAP data cubes}, author={Sarawagi, Sunita and Agrawal, Rakesh and Megiddo, Nimrod}, year={1998}, publisher={Springer} } @article{hu2011stream, title={Stream Database Survey}, author={Hu, Bo}, year={2011} } @article{dean2008mapreduce, title={MapReduce: simplified data processing on large clusters}, author={Dean, Jeffrey and Ghemawat, Sanjay}, journal={Communications of the ACM}, volume={51}, number={1}, pages={107--113}, year={2008}, publisher={ACM} } @misc{linkedin2013senseidb, author = {LinkedIn}, title = {SenseiDB}, month = {July}, year = {2013}, howpublished = "\url{http://www.senseidb.com/}" } @misc{apache2013solr, author = {Apache}, title = {Apache Solr}, month = {February}, year = {2013}, howpublished = "\url{http://lucene.apache.org/solr/}" } @misc{banon2013elasticsearch, author = {Banon, Shay}, title = {ElasticSearch}, month = {July}, year = {2013}, howpublished = "\url{http://www.elasticseach.com/}" } @book{oehler2012ibm, title={IBM Cognos TM1: The Official Guide}, author={Oehler, Karsten and Gruenes, Jochen and Ilacqua, Christopher and Perez, Manuel}, year={2012}, publisher={McGraw-Hill} } @book{schrader2009oracle, title={Oracle Essbase \& Oracle OLAP}, author={Schrader, Michael and Vlamis, Dan and Nader, Mike and Claterbos, Chris and Collins, Dave and Campbell, Mitch and Conrad, Floyd}, year={2009}, publisher={McGraw-Hill, Inc.} } @book{lachev2005applied, title={Applied Microsoft Analysis Services 2005: And Microsoft Business Intelligence Platform}, author={Lachev, Teo}, year={2005}, publisher={Prologika Press} } @article{o1996log, title={The log-structured merge-tree (LSM-tree)}, author={O’Neil, Patrick and Cheng, Edward and Gawlick, Dieter and O’Neil, Elizabeth}, journal={Acta Informatica}, volume={33}, number={4}, pages={351--385}, year={1996}, publisher={Springer} } @inproceedings{o1997improved, title={Improved query performance with variant indexes}, author={O'Neil, Patrick and Quass, Dallan}, booktitle={ACM Sigmod Record}, volume={26}, number={2}, pages={38--49}, year={1997}, organization={ACM} } @inproceedings{cipar2012lazybase, title={LazyBase: trading freshness for performance in a scalable database}, author={Cipar, James and Ganger, Greg and Keeton, Kimberly and Morrey III, Charles B and Soules, Craig AN and Veitch, Alistair}, booktitle={Proceedings of the 7th ACM european conference on Computer Systems}, pages={169--182}, year={2012}, organization={ACM} } @article{collet2013lz4, title={LZ4: Extremely fast compression algorithm}, author={Collet, Yann}, journal={code. google. com}, year={2013} } @inproceedings{beyer1999bottom, title={Bottom-up computation of sparse and iceberg cube}, author={Beyer, Kevin and Ramakrishnan, Raghu}, booktitle={ACM SIGMOD Record}, volume={28}, number={2}, pages={359--370}, year={1999}, organization={ACM} } @inproceedings{vavilapalli2013apache, title={Apache hadoop yarn: Yet another resource negotiator}, author={Vavilapalli, Vinod Kumar and Murthy, Arun C and Douglas, Chris and Agarwal, Sharad and Konar, Mahadev and Evans, Robert and Graves, Thomas and Lowe, Jason and Shah, Hitesh and Seth, Siddharth and others}, booktitle={Proceedings of the 4th annual Symposium on Cloud Computing}, pages={5}, year={2013}, organization={ACM} } @article{boykin2014summingbird, title={Summingbird: A Framework for Integrating Batch and Online MapReduce Computations}, author={Boykin, Oscar and Ritchie, Sam and O’Connell, Ian and Lin, Jimmy}, journal={Proceedings of the VLDB Endowment}, volume={7}, number={13}, year={2014} } @inproceedings{zaharia2012resilient, title={Resilient distributed datasets: A fault-tolerant abstraction for in-memory cluster computing}, author={Zaharia, Matei and Chowdhury, Mosharaf and Das, Tathagata and Dave, Ankur and Ma, Justin and McCauley, Murphy and Franklin, Michael J and Shenker, Scott and Stoica, Ion}, booktitle={Proceedings of the 9th USENIX conference on Networked Systems Design and Implementation}, pages={2--2}, year={2012}, organization={USENIX Association} } @inproceedings{stonebraker2009requirements, title={Requirements for Science Data Bases and SciDB.}, author={Stonebraker, Michael and Becla, Jacek and DeWitt, David J and Lim, Kian-Tat and Maier, David and Ratzesberger, Oliver and Zdonik, Stanley B}, booktitle={CIDR}, volume={7}, pages={173--184}, year={2009} } @article{stonebraker2010mapreduce, title={MapReduce and parallel DBMSs: friends or foes?}, author={Stonebraker, Michael and Abadi, Daniel and DeWitt, David J and Madden, Sam and Paulson, Erik and Pavlo, Andrew and Rasin, Alexander}, journal={Communications of the ACM}, volume={53}, number={1}, pages={64--71}, year={2010}, publisher={ACM} }